[SCM] Samba Shared Repository - branch v3-2-test updated - initial-v3-2-test-2626-g719527f

[David Collier-Brown]

  Just make the size settable, so we can experiment with
settings.  And that Windows result sounds interesting:
it implies a weaker readahead/coalescence algorithm than 
Linux or Solaris.

--dave

Volker Lendecke wrote:
> On Sat, Mar 01, 2008 at 09:40:09AM +0100, Volker Lendecke wrote:
> 
>>Ok, removed the async code again. A lot more investigation
>>is necessary to find something sane.
> 
> 
> Just FYI: Jeremy used as much pressure as is possible to use
> with more than 5000 miles distance to put it in again.
> 
> My tests showed a performance improvement against Windows
> that he did not want to miss: 34MB/sec vs 49MB/sec which is
> roughly 44% more read performance.
> 
> If you have any points that give further improvement, please
> tell me.
> 
> Volker

-- 
David Collier-Brown            | Always do right. This will gratify
Sun Microsystems, Toronto      | some people and astonish the rest
davecb at sun.com                 |                      -- Mark Twain
(905) 943-1983, cell: (647) 833-9377, home off: (416) 223-5943 
(800) 555-9786 x56583, bridge: (877) 385-4099 code: 506 9191#